Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names and initials of individuals, likely in a formal or document context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.46
    1:0.02
    2:0.04
    3:0.03
    4:0.05
    5:0.03
    6:0.05
    7:0.03
    8:0.03
    9:0.08
    10:0.06
    11:0.07
    Negative Logits
     Cancel
    -2.08
    Released
    -1.74
     quote
    -1.65
    netflix
    -1.62
    BuyableInstoreAndOnline
    -1.61
    DoS
    -1.59
    ヘラ
    -1.52
    psc
    -1.48
     Retrieved
    -1.46
    ANE
    -1.44
    POSITIVE LOGITS
    .,
    2.31
     Md
    1.96
    \.
    1.94
    .-
    1.90
    ._
    1.89
    ��
    1.86
     Machina
    1.81
    ��
    1.73
    ./
    1.65
    .;
    1.62
    Act Density 0.013%

    No Known Activations